Análisis de modelos SOM - Frecuencia datos de entrada: semana

Modelo

• ID: 146
• Descripción:
• Frecuencia: semana
• Variables: fecha_cnt, tmax, tmin, longitud, latitud, altitud
• Dimensiones del mapa: 5,5
• Iteraciones: 10000
• Parámetros adicionales:

source("../../lib/som-utils.R")

Attaching package: 'dplyr'

The following objects are masked from 'package:stats':

    filter, lag

The following objects are masked from 'package:base':

    intersect, setdiff, setequal, union

source("../../lib/maps-utils.R")

Linking to GEOS 3.8.0, GDAL 3.0.4, PROJ 6.3.1

Carga del modelo desde disco

mpr.set_base_path_analysis()
model <- mpr.load_model("som-146.rds.xz")
summary(model)

SOM of size 5x5 with a hexagonal topology and a bubble neighbourhood function.
The number of data layers is 1.
Distance measure(s) used: sumofsquares.
Training data included: 156652 objects.
Mean distance to the closest unit in the map: 0.762.

plot(model, type="changes")

Carga del dataset de entrada

df <- mpr.load_data("datos_semana_2k.csv.xz")

df

summary(df)

 id_estacion           fecha             fecha_cnt          tmax       
 Length:156652      Length:156652      Min.   : 1.00   Min.   :-109.0  
 Class :character   Class :character   1st Qu.:13.00   1st Qu.: 147.0  
 Mode  :character   Mode  :character   Median :27.00   Median : 201.0  
                                       Mean   :26.53   Mean   : 202.1  
                                       3rd Qu.:40.00   3rd Qu.: 262.0  
                                       Max.   :53.00   Max.   : 442.0  
      tmin             precip           nevada    prof_nieve      
 Min.   :-189.00   Min.   :  0.00   Min.   :0   Min.   :   0.000  
 1st Qu.:  48.00   1st Qu.:  0.00   1st Qu.:0   1st Qu.:   0.000  
 Median :  98.00   Median :  3.00   Median :0   Median :   0.000  
 Mean   :  98.13   Mean   : 16.92   Mean   :0   Mean   :   0.604  
 3rd Qu.: 152.00   3rd Qu.: 20.00   3rd Qu.:0   3rd Qu.:   0.000  
 Max.   : 272.00   Max.   :690.00   Max.   :0   Max.   :1073.000  
    longitud        latitud           altitud      
 Min.   :27.82   Min.   :-17.889   Min.   :   1.0  
 1st Qu.:39.01   1st Qu.: -4.850   1st Qu.:  44.0  
 Median :41.22   Median : -1.411   Median : 263.0  
 Mean   :40.05   Mean   : -2.426   Mean   : 478.5  
 3rd Qu.:42.19   3rd Qu.:  1.272   3rd Qu.: 687.0  
 Max.   :43.57   Max.   :  4.216   Max.   :2535.0  

Carga de los mapas

world <- ne_countries(scale = "medium", returnclass = "sf")
spain <- subset(world, admin == "Spain")

Mapa de densidad

plot(model, type="count", shape = "straight", palette.name = mpr.degrade.bleu)

Número de elementos en cada celda:

nb <- table(model$unit.classif)
print(nb)

    1     2     3     4     5     6     7     8     9    10    11    12    13 
 1129  4802  8754 11403  6494  8667  3808  6129  7412  8073  6526  6818  6794 
   14    15    16    17    18    19    20    21    22    23    24    25 
 2170  3523 13006  5402  3958  5726  7587  6399  7265  3924  7436  3447 

Comprobación de nodos vacíos:

dim_model <- 5*5;
len_nb = length(nb);
empty_nodes <- dim_model != len_nb;
if (empty_nodes) {
  print(paste("[Warning] Existen nodos vacíos: ", len_nb, "/", dim_model))
}

Mapa de distancia entre vecinos

plot(model, type="dist.neighbours", shape = "straight")

Influencia de las variables

model_colnames = c("fecha_cnt", "tmax", "tmin", "longitud", "latitud", "altitud")
model_ncol = length(model_colnames)

Mapa de variables.

plot(model, shape = "straight")

Mapa de calor por variable

par(mfrow=c(3,4))
for (j in 1:model_ncol) {
  plot(model, type="property", property=getCodes(model,1)[,j],
    palette.name=mpr.coolBlueHotRed,
    main=model_colnames[j],
    cex=0.5, shape = "straight")
}

Correlación para cada columna del vector de nodos

if (!empty_nodes) {
  cor <- apply(getCodes(model,1), 2, mpr.weighted.correlation, w=nb, som=model)
  print(cor)
}

      fecha_cnt       tmax       tmin  longitud   latitud    altitud
[1,] -0.1258577 -0.7863477 -0.8776624 0.4875899 0.3554488 0.33366235
[2,]  0.8367984  0.2412784  0.2400860 0.2108061 0.1860183 0.06316609

Representación de cada variable en un mapa de factores:

if (!empty_nodes) {
  par(mfrow=c(1,1))
  plot(cor[1,], cor[2,], xlim=c(-1,1), ylim=c(-1,1), type="n")
  lines(c(-1,1),c(0,0))
  lines(c(0,0),c(-1,1))
  text(cor[1,], cor[2,], labels=model_colnames, cex=0.75)
  symbols(0,0,circles=1,inches=F,add=T)
}

Importancia de cada variable - varianza ponderada por el tamaño de la celda:

if (!empty_nodes) {
  sigma2 <- sqrt(apply(getCodes(model,1),2,function(x,effectif)
     {m<-sum(effectif*(x-weighted.mean(x,effectif))^2)/(sum(effectif)-1)},
     effectif=nb))
  print(sort(sigma2,decreasing=T))
}

 longitud   altitud      tmax   latitud fecha_cnt      tmin 
0.9620169 0.9448578 0.9339194 0.9333579 0.9278264 0.9161442 

Clustering

if (!empty_nodes) {
  hac <- mpr.hac(model, nb)
}

Visualización de 3 clústeres:

if (!empty_nodes) {
  plot(hac, hang=-1, labels=F)
  rect.hclust(hac, k=3)
}

Visualización de los clústers en el mapa

A qué clúster pertenece cada nodo del mapa de kohonen:

if (!empty_nodes) {
  groups <- cutree(hac, k=3)
  plot(model, type="mapping",
    bgcol=c("steelblue1","sienna1","yellowgreen","red","blue","yellow","purple","green","white","#1f77b4", '#ff7f0e', '#2ca02c', '#d62728', '#9467bd', '#8c564b', '#e377c2')[groups],
    shape = "straight", labels = "")
  add.cluster.boundaries(model, clustering=groups)
}

Análisis de las observaciones de cada cluster

if (!empty_nodes) {
  # Asignamos a cada registro su clúster
  df$cluster <- groups[model$unit.classif]
}

Nuevos dataframes por cluster

if (!empty_nodes) {
  # Creo nuevos dataframes, uno por cada clúster.
  df.cluster01 <- subset(df, cluster==1)
  df.cluster02 <- subset(df, cluster==2)
  df.cluster03 <- subset(df, cluster==3)

  # Extraigo del dataframe las features.
  df.cluster01 <- select(df.cluster01, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster02 <- select(df.cluster02, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster03 <- select(df.cluster03, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
}

if (!empty_nodes) summary(df.cluster01)

   fecha_cnt         tmax            tmin         precip           nevada 
 Min.   : 1.0   Min.   : -5.0   Min.   :-51   Min.   :  0.00   Min.   :0  
 1st Qu.:13.0   1st Qu.:211.0   1st Qu.:148   1st Qu.:  0.00   1st Qu.:0  
 Median :26.0   Median :234.0   Median :172   Median :  0.00   Median :0  
 Mean   :26.3   Mean   :229.4   Mean   :165   Mean   :  6.28   Mean   :0  
 3rd Qu.:39.0   3rd Qu.:262.0   3rd Qu.:201   3rd Qu.:  2.00   3rd Qu.:0  
 Max.   :53.0   Max.   :384.0   Max.   :263   Max.   :490.00   Max.   :0  
   prof_nieve    longitud        latitud          altitud      
 Min.   :0    Min.   :27.82   Min.   :-17.89   Min.   :  14.0  
 1st Qu.:0    1st Qu.:28.05   1st Qu.:-16.56   1st Qu.:  25.0  
 Median :0    Median :28.44   Median :-16.33   Median :  33.0  
 Mean   :0    Mean   :28.35   Mean   :-16.04   Mean   : 371.2  
 3rd Qu.:0    3rd Qu.:28.48   3rd Qu.:-15.39   3rd Qu.:  64.0  
 Max.   :0    Max.   :28.95   Max.   :-13.60   Max.   :2371.0  

if (!empty_nodes) summary(df.cluster02)

   fecha_cnt          tmax            tmin            precip           nevada 
 Min.   : 1.00   Min.   :-31.0   Min.   :-161.0   Min.   :  0.00   Min.   :0  
 1st Qu.:13.00   1st Qu.:152.0   1st Qu.:  52.0   1st Qu.:  0.00   1st Qu.:0  
 Median :26.00   Median :203.0   Median :  99.0   Median :  3.00   Median :0  
 Mean   :26.51   Mean   :208.6   Mean   :  99.4   Mean   : 16.49   Mean   :0  
 3rd Qu.:40.00   3rd Qu.:267.0   3rd Qu.: 149.0   3rd Qu.: 20.00   3rd Qu.:0  
 Max.   :53.00   Max.   :442.0   Max.   : 272.0   Max.   :690.00   Max.   :0  
   prof_nieve           longitud        latitud          altitud    
 Min.   :  0.00000   Min.   :35.28   Min.   :-8.624   Min.   :   1  
 1st Qu.:  0.00000   1st Qu.:39.56   1st Qu.:-4.488   1st Qu.:  52  
 Median :  0.00000   Median :41.29   Median :-1.293   Median : 258  
 Mean   :  0.06506   Mean   :40.73   Mean   :-1.679   Mean   : 368  
 3rd Qu.:  0.00000   3rd Qu.:42.12   3rd Qu.: 1.296   3rd Qu.: 628  
 Max.   :299.00000   Max.   :43.57   Max.   : 4.216   Max.   :1894  

if (!empty_nodes) summary(df.cluster03)

   fecha_cnt          tmax              tmin             precip     
 Min.   : 1.00   Min.   :-109.00   Min.   :-189.00   Min.   :  0.0  
 1st Qu.:14.00   1st Qu.:  29.00   1st Qu.: -33.00   1st Qu.:  3.0  
 Median :27.00   Median :  76.00   Median :  10.00   Median : 19.0  
 Mean   :26.92   Mean   :  81.71   Mean   :  12.07   Mean   : 33.9  
 3rd Qu.:40.00   3rd Qu.: 136.00   3rd Qu.:  60.00   3rd Qu.: 48.0  
 Max.   :53.00   Max.   : 249.00   Max.   : 154.00   Max.   :615.0  
     nevada    prof_nieve          longitud        latitud       
 Min.   :0   Min.   :   0.000   Min.   :40.78   Min.   :-4.0103  
 1st Qu.:0   1st Qu.:   0.000   1st Qu.:42.18   1st Qu.: 0.7789  
 Median :0   Median :   0.000   Median :42.47   Median : 1.0544  
 Mean   :0   Mean   :   8.879   Mean   :42.25   Mean   : 0.7657  
 3rd Qu.:0   3rd Qu.:   0.000   3rd Qu.:42.64   3rd Qu.: 1.7150  
 Max.   :0   Max.   :1073.000   Max.   :42.77   Max.   : 2.4378  
    altitud    
 Min.   :1056  
 1st Qu.:1971  
 Median :2230  
 Mean   :2157  
 3rd Qu.:2400  
 Max.   :2535  

Número de elementos en cada clúster

if (!empty_nodes) {
  df.clusters.dim <- c(dim(df.cluster01)[1], dim(df.cluster02)[1], dim(df.cluster03)[1])
  barplot(df.clusters.dim,
          names.arg = c("cluster01", "cluster02", "cluster03"),
          col = "steelblue1")
}

Distribución de los datos

if (!empty_nodes) mpr.hist(df.cluster01)

if (!empty_nodes) mpr.hist(df.cluster02)

if (!empty_nodes) mpr.hist(df.cluster03)

if (!empty_nodes) mpr.boxplot(df.cluster01)
if (!empty_nodes) mpr.boxplot(df.cluster02)

if (!empty_nodes) mpr.boxplot(df.cluster03)

Localización geográfica de las estaciones de medida de cada cluster

# Agrupa por longitud y latitud para rellenar el mapa con menos datos.
if (!empty_nodes) {
  df.cluster01.grouped <- mpr.group_by_geo(df.cluster01)
  df.cluster02.grouped <- mpr.group_by_geo(df.cluster02)
  df.cluster03.grouped <- mpr.group_by_geo(df.cluster03)
}

if (!empty_nodes) mpr.draw_map(spain, df.cluster01.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster02.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster03.grouped)

Visualización de 4 clústeres:

if (!empty_nodes) {
  plot(hac, hang=-1, labels=F)
  rect.hclust(hac, k=4)
}

Visualización de los clústers en el mapa

A qué clúster pertenece cada nodo del mapa de kohonen:

if (!empty_nodes) {
  groups <- cutree(hac, k=4)
  plot(model, type="mapping",
    bgcol=c("steelblue1","sienna1","yellowgreen","red","blue","yellow","purple","green","white","#1f77b4", '#ff7f0e', '#2ca02c', '#d62728', '#9467bd', '#8c564b', '#e377c2')[groups],
    shape = "straight", labels = "")
  add.cluster.boundaries(model, clustering=groups)
}

Análisis de las observaciones de cada cluster

if (!empty_nodes) {
  # Asignamos a cada registro su clúster
  df$cluster <- groups[model$unit.classif]
}

Nuevos dataframes por cluster

if (!empty_nodes) {
  # Creo nuevos dataframes, uno por cada clúster.
  df.cluster01 <- subset(df, cluster==1)
  df.cluster02 <- subset(df, cluster==2)
  df.cluster03 <- subset(df, cluster==3)
  df.cluster04 <- subset(df, cluster==4)

  # Extraigo del dataframe las features.
  df.cluster01 <- select(df.cluster01, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster02 <- select(df.cluster02, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster03 <- select(df.cluster03, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster04 <- select(df.cluster04, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
}

if (!empty_nodes) summary(df.cluster01)

   fecha_cnt         tmax            tmin         precip           nevada 
 Min.   : 1.0   Min.   : -5.0   Min.   :-51   Min.   :  0.00   Min.   :0  
 1st Qu.:13.0   1st Qu.:211.0   1st Qu.:148   1st Qu.:  0.00   1st Qu.:0  
 Median :26.0   Median :234.0   Median :172   Median :  0.00   Median :0  
 Mean   :26.3   Mean   :229.4   Mean   :165   Mean   :  6.28   Mean   :0  
 3rd Qu.:39.0   3rd Qu.:262.0   3rd Qu.:201   3rd Qu.:  2.00   3rd Qu.:0  
 Max.   :53.0   Max.   :384.0   Max.   :263   Max.   :490.00   Max.   :0  
   prof_nieve    longitud        latitud          altitud      
 Min.   :0    Min.   :27.82   Min.   :-17.89   Min.   :  14.0  
 1st Qu.:0    1st Qu.:28.05   1st Qu.:-16.56   1st Qu.:  25.0  
 Median :0    Median :28.44   Median :-16.33   Median :  33.0  
 Mean   :0    Mean   :28.35   Mean   :-16.04   Mean   : 371.2  
 3rd Qu.:0    3rd Qu.:28.48   3rd Qu.:-15.39   3rd Qu.:  64.0  
 Max.   :0    Max.   :28.95   Max.   :-13.60   Max.   :2371.0  

if (!empty_nodes) summary(df.cluster02)

   fecha_cnt          tmax            tmin             precip           nevada 
 Min.   : 1.00   Min.   :-22.0   Min.   :-161.00   Min.   :  0.00   Min.   :0  
 1st Qu.: 6.00   1st Qu.:134.0   1st Qu.:  31.00   1st Qu.:  0.00   1st Qu.:0  
 Median :11.00   Median :168.0   Median :  65.00   Median :  6.00   Median :0  
 Mean   :11.38   Mean   :168.5   Mean   :  63.78   Mean   : 18.56   Mean   :0  
 3rd Qu.:17.00   3rd Qu.:203.0   3rd Qu.:  97.00   3rd Qu.: 24.00   3rd Qu.:0  
 Max.   :31.00   Max.   :327.0   Max.   : 195.00   Max.   :608.00   Max.   :0  
   prof_nieve          longitud        latitud          altitud      
 Min.   :  0.0000   Min.   :35.28   Min.   :-8.624   Min.   :   1.0  
 1st Qu.:  0.0000   1st Qu.:39.49   1st Qu.:-4.127   1st Qu.:  47.0  
 Median :  0.0000   Median :41.29   Median :-1.169   Median : 251.0  
 Mean   :  0.1057   Mean   :40.71   Mean   :-1.577   Mean   : 360.4  
 3rd Qu.:  0.0000   3rd Qu.:42.11   3rd Qu.: 1.363   3rd Qu.: 626.0  
 Max.   :299.0000   Max.   :43.57   Max.   : 4.216   Max.   :1894.0  

if (!empty_nodes) summary(df.cluster03)

   fecha_cnt          tmax            tmin            precip           nevada 
 Min.   :13.00   Min.   :-31.0   Min.   :-155.0   Min.   :  0.00   Min.   :0  
 1st Qu.:30.00   1st Qu.:181.0   1st Qu.:  83.0   1st Qu.:  0.00   1st Qu.:0  
 Median :37.00   Median :249.0   Median : 132.0   Median :  2.00   Median :0  
 Mean   :37.23   Mean   :236.9   Mean   : 124.6   Mean   : 15.02   Mean   :0  
 3rd Qu.:45.00   3rd Qu.:295.0   3rd Qu.: 172.0   3rd Qu.: 16.00   3rd Qu.:0  
 Max.   :53.00   Max.   :442.0   Max.   : 272.0   Max.   :690.00   Max.   :0  
   prof_nieve           longitud        latitud          altitud      
 Min.   :  0.00000   Min.   :35.28   Min.   :-8.624   Min.   :   1.0  
 1st Qu.:  0.00000   1st Qu.:39.56   1st Qu.:-4.488   1st Qu.:  52.0  
 Median :  0.00000   Median :41.29   Median :-1.411   Median : 261.0  
 Mean   :  0.03625   Mean   :40.75   Mean   :-1.752   Mean   : 373.4  
 3rd Qu.:  0.00000   3rd Qu.:42.12   3rd Qu.: 1.179   3rd Qu.: 639.0  
 Max.   :290.00000   Max.   :43.57   Max.   : 4.216   Max.   :1894.0  

if (!empty_nodes) summary(df.cluster04)

   fecha_cnt          tmax              tmin             precip     
 Min.   : 1.00   Min.   :-109.00   Min.   :-189.00   Min.   :  0.0  
 1st Qu.:14.00   1st Qu.:  29.00   1st Qu.: -33.00   1st Qu.:  3.0  
 Median :27.00   Median :  76.00   Median :  10.00   Median : 19.0  
 Mean   :26.92   Mean   :  81.71   Mean   :  12.07   Mean   : 33.9  
 3rd Qu.:40.00   3rd Qu.: 136.00   3rd Qu.:  60.00   3rd Qu.: 48.0  
 Max.   :53.00   Max.   : 249.00   Max.   : 154.00   Max.   :615.0  
     nevada    prof_nieve          longitud        latitud       
 Min.   :0   Min.   :   0.000   Min.   :40.78   Min.   :-4.0103  
 1st Qu.:0   1st Qu.:   0.000   1st Qu.:42.18   1st Qu.: 0.7789  
 Median :0   Median :   0.000   Median :42.47   Median : 1.0544  
 Mean   :0   Mean   :   8.879   Mean   :42.25   Mean   : 0.7657  
 3rd Qu.:0   3rd Qu.:   0.000   3rd Qu.:42.64   3rd Qu.: 1.7150  
 Max.   :0   Max.   :1073.000   Max.   :42.77   Max.   : 2.4378  
    altitud    
 Min.   :1056  
 1st Qu.:1971  
 Median :2230  
 Mean   :2157  
 3rd Qu.:2400  
 Max.   :2535  

Número de elementos en cada clúster

if (!empty_nodes) {
  df.clusters.dim <- c(dim(df.cluster01)[1], dim(df.cluster02)[1], dim(df.cluster03)[1], dim(df.cluster04)[1])
  barplot(df.clusters.dim,
          names.arg = c("cluster01", "cluster02", "cluster03", "cluster04"),
          col = "steelblue1")
}

Distribución de los datos

if (!empty_nodes) mpr.hist(df.cluster01)

if (!empty_nodes) mpr.hist(df.cluster02)

if (!empty_nodes) mpr.hist(df.cluster03)

if (!empty_nodes) mpr.hist(df.cluster04)

if (!empty_nodes) mpr.boxplot(df.cluster01)
if (!empty_nodes) mpr.boxplot(df.cluster02)

if (!empty_nodes) mpr.boxplot(df.cluster03)

if (!empty_nodes) mpr.boxplot(df.cluster04)

Localización geográfica de las estaciones de medida de cada cluster

# Agrupa por longitud y latitud para rellenar el mapa con menos datos.
if (!empty_nodes) {
  df.cluster01.grouped <- mpr.group_by_geo(df.cluster01)
  df.cluster02.grouped <- mpr.group_by_geo(df.cluster02)
  df.cluster03.grouped <- mpr.group_by_geo(df.cluster03)
  df.cluster04.grouped <- mpr.group_by_geo(df.cluster04)
}

if (!empty_nodes) mpr.draw_map(spain, df.cluster01.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster02.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster03.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster04.grouped)

Visualización de 5 clústeres:

if (!empty_nodes) {
  plot(hac, hang=-1, labels=F)
  rect.hclust(hac, k=5)
}

Visualización de los clústers en el mapa

A qué clúster pertenece cada nodo del mapa de kohonen:

if (!empty_nodes) {
  groups <- cutree(hac, k=5)
  plot(model, type="mapping",
    bgcol=c("steelblue1","sienna1","yellowgreen","red","blue","yellow","purple","green","white","#1f77b4", '#ff7f0e', '#2ca02c', '#d62728', '#9467bd', '#8c564b', '#e377c2')[groups],
    shape = "straight", labels = "")
  add.cluster.boundaries(model, clustering=groups)
}

Análisis de las observaciones de cada cluster

if (!empty_nodes) {
  # Asignamos a cada registro su clúster
  df$cluster <- groups[model$unit.classif]
}

Nuevos dataframes por cluster

if (!empty_nodes) {
  # Creo nuevos dataframes, uno por cada clúster.
  df.cluster01 <- subset(df, cluster==1)
  df.cluster02 <- subset(df, cluster==2)
  df.cluster03 <- subset(df, cluster==3)
  df.cluster04 <- subset(df, cluster==4)
  df.cluster05 <- subset(df, cluster==5)

  # Extraigo del dataframe las features.
  df.cluster01 <- select(df.cluster01, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster02 <- select(df.cluster02, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster03 <- select(df.cluster03, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster04 <- select(df.cluster04, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster05 <- select(df.cluster05, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
}

if (!empty_nodes) summary(df.cluster01)

   fecha_cnt         tmax            tmin         precip           nevada 
 Min.   : 1.0   Min.   : -5.0   Min.   :-51   Min.   :  0.00   Min.   :0  
 1st Qu.:13.0   1st Qu.:211.0   1st Qu.:148   1st Qu.:  0.00   1st Qu.:0  
 Median :26.0   Median :234.0   Median :172   Median :  0.00   Median :0  
 Mean   :26.3   Mean   :229.4   Mean   :165   Mean   :  6.28   Mean   :0  
 3rd Qu.:39.0   3rd Qu.:262.0   3rd Qu.:201   3rd Qu.:  2.00   3rd Qu.:0  
 Max.   :53.0   Max.   :384.0   Max.   :263   Max.   :490.00   Max.   :0  
   prof_nieve    longitud        latitud          altitud      
 Min.   :0    Min.   :27.82   Min.   :-17.89   Min.   :  14.0  
 1st Qu.:0    1st Qu.:28.05   1st Qu.:-16.56   1st Qu.:  25.0  
 Median :0    Median :28.44   Median :-16.33   Median :  33.0  
 Mean   :0    Mean   :28.35   Mean   :-16.04   Mean   : 371.2  
 3rd Qu.:0    3rd Qu.:28.48   3rd Qu.:-15.39   3rd Qu.:  64.0  
 Max.   :0    Max.   :28.95   Max.   :-13.60   Max.   :2371.0  

if (!empty_nodes) summary(df.cluster02)

   fecha_cnt          tmax            tmin             precip           nevada 
 Min.   : 1.00   Min.   :-22.0   Min.   :-161.00   Min.   :  0.00   Min.   :0  
 1st Qu.: 6.00   1st Qu.:134.0   1st Qu.:  31.00   1st Qu.:  0.00   1st Qu.:0  
 Median :11.00   Median :168.0   Median :  65.00   Median :  6.00   Median :0  
 Mean   :11.38   Mean   :168.5   Mean   :  63.78   Mean   : 18.56   Mean   :0  
 3rd Qu.:17.00   3rd Qu.:203.0   3rd Qu.:  97.00   3rd Qu.: 24.00   3rd Qu.:0  
 Max.   :31.00   Max.   :327.0   Max.   : 195.00   Max.   :608.00   Max.   :0  
   prof_nieve          longitud        latitud          altitud      
 Min.   :  0.0000   Min.   :35.28   Min.   :-8.624   Min.   :   1.0  
 1st Qu.:  0.0000   1st Qu.:39.49   1st Qu.:-4.127   1st Qu.:  47.0  
 Median :  0.0000   Median :41.29   Median :-1.169   Median : 251.0  
 Mean   :  0.1057   Mean   :40.71   Mean   :-1.577   Mean   : 360.4  
 3rd Qu.:  0.0000   3rd Qu.:42.11   3rd Qu.: 1.363   3rd Qu.: 626.0  
 Max.   :299.0000   Max.   :43.57   Max.   : 4.216   Max.   :1894.0  

if (!empty_nodes) summary(df.cluster03)

   fecha_cnt          tmax            tmin           precip            nevada 
 Min.   :14.00   Min.   :164.0   Min.   : 39.0   Min.   :  0.000   Min.   :0  
 1st Qu.:27.00   1st Qu.:262.0   1st Qu.:134.0   1st Qu.:  0.000   1st Qu.:0  
 Median :32.00   Median :289.0   Median :165.0   Median :  0.000   Median :0  
 Mean   :32.22   Mean   :288.5   Mean   :163.2   Mean   :  9.955   Mean   :0  
 3rd Qu.:37.00   3rd Qu.:315.0   3rd Qu.:191.0   3rd Qu.:  9.000   3rd Qu.:0  
 Max.   :53.00   Max.   :442.0   Max.   :272.0   Max.   :610.000   Max.   :0  
   prof_nieve          longitud        latitud           altitud      
 Min.   :  0.0000   Min.   :35.28   Min.   :-8.6239   Min.   :   1.0  
 1st Qu.:  0.0000   1st Qu.:38.99   1st Qu.:-3.7225   1st Qu.:  43.3  
 Median :  0.0000   Median :40.95   Median : 0.3264   Median : 247.0  
 Mean   :  0.0048   Mean   :40.33   Mean   :-0.9801   Mean   : 361.9  
 3rd Qu.:  0.0000   3rd Qu.:41.67   3rd Qu.: 1.4181   3rd Qu.: 628.0  
 Max.   :173.0000   Max.   :43.36   Max.   : 4.2156   Max.   :1894.0  

if (!empty_nodes) summary(df.cluster04)

   fecha_cnt          tmax            tmin             precip           nevada 
 Min.   :13.00   Min.   :-31.0   Min.   :-155.00   Min.   :  0.00   Min.   :0  
 1st Qu.:41.00   1st Qu.:132.0   1st Qu.:  38.00   1st Qu.:  0.00   1st Qu.:0  
 Median :46.00   Median :170.0   Median :  74.00   Median :  7.00   Median :0  
 Mean   :43.73   Mean   :169.9   Mean   :  74.51   Mean   : 21.61   Mean   :0  
 3rd Qu.:49.00   3rd Qu.:208.0   3rd Qu.: 112.00   3rd Qu.: 27.00   3rd Qu.:0  
 Max.   :53.00   Max.   :346.0   Max.   : 211.00   Max.   :690.00   Max.   :0  
   prof_nieve           longitud        latitud           altitud      
 Min.   :  0.00000   Min.   :35.28   Min.   :-8.6239   Min.   :   1.0  
 1st Qu.:  0.00000   1st Qu.:40.66   1st Qu.:-5.6983   1st Qu.:  61.0  
 Median :  0.00000   Median :41.70   Median :-2.9056   Median : 316.0  
 Mean   :  0.07711   Mean   :41.30   Mean   :-2.7542   Mean   : 388.4  
 3rd Qu.:  0.00000   3rd Qu.:42.70   3rd Qu.: 0.7433   3rd Qu.: 656.0  
 Max.   :290.00000   Max.   :43.57   Max.   : 4.2156   Max.   :1572.0  

if (!empty_nodes) summary(df.cluster05)

   fecha_cnt          tmax              tmin             precip     
 Min.   : 1.00   Min.   :-109.00   Min.   :-189.00   Min.   :  0.0  
 1st Qu.:14.00   1st Qu.:  29.00   1st Qu.: -33.00   1st Qu.:  3.0  
 Median :27.00   Median :  76.00   Median :  10.00   Median : 19.0  
 Mean   :26.92   Mean   :  81.71   Mean   :  12.07   Mean   : 33.9  
 3rd Qu.:40.00   3rd Qu.: 136.00   3rd Qu.:  60.00   3rd Qu.: 48.0  
 Max.   :53.00   Max.   : 249.00   Max.   : 154.00   Max.   :615.0  
     nevada    prof_nieve          longitud        latitud       
 Min.   :0   Min.   :   0.000   Min.   :40.78   Min.   :-4.0103  
 1st Qu.:0   1st Qu.:   0.000   1st Qu.:42.18   1st Qu.: 0.7789  
 Median :0   Median :   0.000   Median :42.47   Median : 1.0544  
 Mean   :0   Mean   :   8.879   Mean   :42.25   Mean   : 0.7657  
 3rd Qu.:0   3rd Qu.:   0.000   3rd Qu.:42.64   3rd Qu.: 1.7150  
 Max.   :0   Max.   :1073.000   Max.   :42.77   Max.   : 2.4378  
    altitud    
 Min.   :1056  
 1st Qu.:1971  
 Median :2230  
 Mean   :2157  
 3rd Qu.:2400  
 Max.   :2535  

Número de elementos en cada clúster

if (!empty_nodes) {
  df.clusters.dim <- c(dim(df.cluster01)[1], dim(df.cluster02)[1], dim(df.cluster03)[1], dim(df.cluster04)[1], dim(df.cluster05)[1])
  barplot(df.clusters.dim,
          names.arg = c("cluster01", "cluster02", "cluster03", "cluster04", "cluster05"),
          col = "steelblue1")
}

Distribución de los datos

if (!empty_nodes) mpr.hist(df.cluster01)

if (!empty_nodes) mpr.hist(df.cluster02)

if (!empty_nodes) mpr.hist(df.cluster03)

if (!empty_nodes) mpr.hist(df.cluster04)

if (!empty_nodes) mpr.hist(df.cluster05)

if (!empty_nodes) mpr.boxplot(df.cluster01)
if (!empty_nodes) mpr.boxplot(df.cluster02)

if (!empty_nodes) mpr.boxplot(df.cluster03)

if (!empty_nodes) mpr.boxplot(df.cluster04)

if (!empty_nodes) mpr.boxplot(df.cluster05)

Localización geográfica de las estaciones de medida de cada cluster

# Agrupa por longitud y latitud para rellenar el mapa con menos datos.
if (!empty_nodes) {
  df.cluster01.grouped <- mpr.group_by_geo(df.cluster01)
  df.cluster02.grouped <- mpr.group_by_geo(df.cluster02)
  df.cluster03.grouped <- mpr.group_by_geo(df.cluster03)
  df.cluster04.grouped <- mpr.group_by_geo(df.cluster04)
  df.cluster05.grouped <- mpr.group_by_geo(df.cluster05)
}

if (!empty_nodes) mpr.draw_map(spain, df.cluster01.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster02.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster03.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster04.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster05.grouped)

Visualización de 6 clústeres:

if (!empty_nodes) {
  plot(hac, hang=-1, labels=F)
  rect.hclust(hac, k=6)
}

Visualización de los clústers en el mapa

A qué clúster pertenece cada nodo del mapa de kohonen:

if (!empty_nodes) {
  groups <- cutree(hac, k=6)
  plot(model, type="mapping",
    bgcol=c("steelblue1","sienna1","yellowgreen","red","blue","yellow","purple","green","white","#1f77b4", '#ff7f0e', '#2ca02c', '#d62728', '#9467bd', '#8c564b', '#e377c2')[groups],
    shape = "straight", labels = "")
  add.cluster.boundaries(model, clustering=groups)
}

Análisis de las observaciones de cada cluster

if (!empty_nodes) {
  # Asignamos a cada registro su clúster
  df$cluster <- groups[model$unit.classif]
}

Nuevos dataframes por cluster

if (!empty_nodes) {
  # Creo nuevos dataframes, uno por cada clúster.
  df.cluster01 <- subset(df, cluster==1)
  df.cluster02 <- subset(df, cluster==2)
  df.cluster03 <- subset(df, cluster==3)
  df.cluster04 <- subset(df, cluster==4)
  df.cluster05 <- subset(df, cluster==5)
  df.cluster06 <- subset(df, cluster==6)

  # Extraigo del dataframe las features.
  df.cluster01 <- select(df.cluster01, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster02 <- select(df.cluster02, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster03 <- select(df.cluster03, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster04 <- select(df.cluster04, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster05 <- select(df.cluster05, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster06 <- select(df.cluster06, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
}

if (!empty_nodes) summary(df.cluster01)

   fecha_cnt          tmax            tmin            precip            nevada 
 Min.   : 1.00   Min.   : -5.0   Min.   :-51.00   Min.   :  0.000   Min.   :0  
 1st Qu.:13.00   1st Qu.:101.0   1st Qu.: 27.00   1st Qu.:  0.000   1st Qu.:0  
 Median :26.00   Median :140.0   Median : 60.00   Median :  0.000   Median :0  
 Mean   :26.33   Mean   :144.1   Mean   : 67.88   Mean   :  9.353   Mean   :0  
 3rd Qu.:39.00   3rd Qu.:190.0   3rd Qu.:109.00   3rd Qu.:  3.000   3rd Qu.:0  
 Max.   :53.00   Max.   :263.0   Max.   :184.00   Max.   :316.000   Max.   :0  
   prof_nieve    longitud        latitud         altitud    
 Min.   :0    Min.   :28.31   Min.   :-16.5   Min.   :2371  
 1st Qu.:0    1st Qu.:28.31   1st Qu.:-16.5   1st Qu.:2371  
 Median :0    Median :28.31   Median :-16.5   Median :2371  
 Mean   :0    Mean   :28.31   Mean   :-16.5   Mean   :2371  
 3rd Qu.:0    3rd Qu.:28.31   3rd Qu.:-16.5   3rd Qu.:2371  
 Max.   :0    Max.   :28.31   Max.   :-16.5   Max.   :2371  

if (!empty_nodes) summary(df.cluster02)

   fecha_cnt          tmax            tmin             precip           nevada 
 Min.   : 1.00   Min.   :-22.0   Min.   :-161.00   Min.   :  0.00   Min.   :0  
 1st Qu.: 6.00   1st Qu.:134.0   1st Qu.:  31.00   1st Qu.:  0.00   1st Qu.:0  
 Median :11.00   Median :168.0   Median :  65.00   Median :  6.00   Median :0  
 Mean   :11.38   Mean   :168.5   Mean   :  63.78   Mean   : 18.56   Mean   :0  
 3rd Qu.:17.00   3rd Qu.:203.0   3rd Qu.:  97.00   3rd Qu.: 24.00   3rd Qu.:0  
 Max.   :31.00   Max.   :327.0   Max.   : 195.00   Max.   :608.00   Max.   :0  
   prof_nieve          longitud        latitud          altitud      
 Min.   :  0.0000   Min.   :35.28   Min.   :-8.624   Min.   :   1.0  
 1st Qu.:  0.0000   1st Qu.:39.49   1st Qu.:-4.127   1st Qu.:  47.0  
 Median :  0.0000   Median :41.29   Median :-1.169   Median : 251.0  
 Mean   :  0.1057   Mean   :40.71   Mean   :-1.577   Mean   : 360.4  
 3rd Qu.:  0.0000   3rd Qu.:42.11   3rd Qu.: 1.363   3rd Qu.: 626.0  
 Max.   :299.0000   Max.   :43.57   Max.   : 4.216   Max.   :1894.0  

if (!empty_nodes) summary(df.cluster03)

   fecha_cnt          tmax            tmin           precip           nevada 
 Min.   : 1.00   Min.   :126.0   Min.   : 67.0   Min.   :  0.00   Min.   :0  
 1st Qu.:13.00   1st Qu.:218.0   1st Qu.:157.0   1st Qu.:  0.00   1st Qu.:0  
 Median :26.00   Median :239.0   Median :177.0   Median :  0.00   Median :0  
 Mean   :26.29   Mean   :240.5   Mean   :177.7   Mean   :  5.88   Mean   :0  
 3rd Qu.:39.00   3rd Qu.:265.0   3rd Qu.:205.0   3rd Qu.:  2.00   3rd Qu.:0  
 Max.   :53.00   Max.   :384.0   Max.   :263.0   Max.   :490.00   Max.   :0  
   prof_nieve    longitud        latitud          altitud     
 Min.   :0    Min.   :27.82   Min.   :-17.89   Min.   : 14.0  
 1st Qu.:0    1st Qu.:28.05   1st Qu.:-17.75   1st Qu.: 25.0  
 Median :0    Median :28.46   Median :-16.33   Median : 33.0  
 Mean   :0    Mean   :28.36   Mean   :-15.98   Mean   :110.7  
 3rd Qu.:0    3rd Qu.:28.63   3rd Qu.:-13.86   3rd Qu.: 64.0  
 Max.   :0    Max.   :28.95   Max.   :-13.60   Max.   :632.0  

if (!empty_nodes) summary(df.cluster04)

   fecha_cnt          tmax            tmin           precip            nevada 
 Min.   :14.00   Min.   :164.0   Min.   : 39.0   Min.   :  0.000   Min.   :0  
 1st Qu.:27.00   1st Qu.:262.0   1st Qu.:134.0   1st Qu.:  0.000   1st Qu.:0  
 Median :32.00   Median :289.0   Median :165.0   Median :  0.000   Median :0  
 Mean   :32.22   Mean   :288.5   Mean   :163.2   Mean   :  9.955   Mean   :0  
 3rd Qu.:37.00   3rd Qu.:315.0   3rd Qu.:191.0   3rd Qu.:  9.000   3rd Qu.:0  
 Max.   :53.00   Max.   :442.0   Max.   :272.0   Max.   :610.000   Max.   :0  
   prof_nieve          longitud        latitud           altitud      
 Min.   :  0.0000   Min.   :35.28   Min.   :-8.6239   Min.   :   1.0  
 1st Qu.:  0.0000   1st Qu.:38.99   1st Qu.:-3.7225   1st Qu.:  43.3  
 Median :  0.0000   Median :40.95   Median : 0.3264   Median : 247.0  
 Mean   :  0.0048   Mean   :40.33   Mean   :-0.9801   Mean   : 361.9  
 3rd Qu.:  0.0000   3rd Qu.:41.67   3rd Qu.: 1.4181   3rd Qu.: 628.0  
 Max.   :173.0000   Max.   :43.36   Max.   : 4.2156   Max.   :1894.0  

if (!empty_nodes) summary(df.cluster05)

   fecha_cnt          tmax            tmin             precip           nevada 
 Min.   :13.00   Min.   :-31.0   Min.   :-155.00   Min.   :  0.00   Min.   :0  
 1st Qu.:41.00   1st Qu.:132.0   1st Qu.:  38.00   1st Qu.:  0.00   1st Qu.:0  
 Median :46.00   Median :170.0   Median :  74.00   Median :  7.00   Median :0  
 Mean   :43.73   Mean   :169.9   Mean   :  74.51   Mean   : 21.61   Mean   :0  
 3rd Qu.:49.00   3rd Qu.:208.0   3rd Qu.: 112.00   3rd Qu.: 27.00   3rd Qu.:0  
 Max.   :53.00   Max.   :346.0   Max.   : 211.00   Max.   :690.00   Max.   :0  
   prof_nieve           longitud        latitud           altitud      
 Min.   :  0.00000   Min.   :35.28   Min.   :-8.6239   Min.   :   1.0  
 1st Qu.:  0.00000   1st Qu.:40.66   1st Qu.:-5.6983   1st Qu.:  61.0  
 Median :  0.00000   Median :41.70   Median :-2.9056   Median : 316.0  
 Mean   :  0.07711   Mean   :41.30   Mean   :-2.7542   Mean   : 388.4  
 3rd Qu.:  0.00000   3rd Qu.:42.70   3rd Qu.: 0.7433   3rd Qu.: 656.0  
 Max.   :290.00000   Max.   :43.57   Max.   : 4.2156   Max.   :1572.0  

if (!empty_nodes) summary(df.cluster06)

   fecha_cnt          tmax              tmin             precip     
 Min.   : 1.00   Min.   :-109.00   Min.   :-189.00   Min.   :  0.0  
 1st Qu.:14.00   1st Qu.:  29.00   1st Qu.: -33.00   1st Qu.:  3.0  
 Median :27.00   Median :  76.00   Median :  10.00   Median : 19.0  
 Mean   :26.92   Mean   :  81.71   Mean   :  12.07   Mean   : 33.9  
 3rd Qu.:40.00   3rd Qu.: 136.00   3rd Qu.:  60.00   3rd Qu.: 48.0  
 Max.   :53.00   Max.   : 249.00   Max.   : 154.00   Max.   :615.0  
     nevada    prof_nieve          longitud        latitud       
 Min.   :0   Min.   :   0.000   Min.   :40.78   Min.   :-4.0103  
 1st Qu.:0   1st Qu.:   0.000   1st Qu.:42.18   1st Qu.: 0.7789  
 Median :0   Median :   0.000   Median :42.47   Median : 1.0544  
 Mean   :0   Mean   :   8.879   Mean   :42.25   Mean   : 0.7657  
 3rd Qu.:0   3rd Qu.:   0.000   3rd Qu.:42.64   3rd Qu.: 1.7150  
 Max.   :0   Max.   :1073.000   Max.   :42.77   Max.   : 2.4378  
    altitud    
 Min.   :1056  
 1st Qu.:1971  
 Median :2230  
 Mean   :2157  
 3rd Qu.:2400  
 Max.   :2535  

Número de elementos en cada clúster

if (!empty_nodes) {
  df.clusters.dim <- c(dim(df.cluster01)[1], dim(df.cluster02)[1], dim(df.cluster03)[1], dim(df.cluster04)[1], dim(df.cluster05)[1], dim(df.cluster06)[1])
  barplot(df.clusters.dim,
          names.arg = c("cluster01", "cluster02", "cluster03", "cluster04", "cluster05", "cluster06"),
          col = "steelblue1")
}

Distribución de los datos

if (!empty_nodes) mpr.hist(df.cluster01)

if (!empty_nodes) mpr.hist(df.cluster02)

if (!empty_nodes) mpr.hist(df.cluster03)

if (!empty_nodes) mpr.hist(df.cluster04)

if (!empty_nodes) mpr.hist(df.cluster05)

if (!empty_nodes) mpr.hist(df.cluster06)

if (!empty_nodes) mpr.boxplot(df.cluster01)
if (!empty_nodes) mpr.boxplot(df.cluster02)

if (!empty_nodes) mpr.boxplot(df.cluster03)

if (!empty_nodes) mpr.boxplot(df.cluster04)

if (!empty_nodes) mpr.boxplot(df.cluster05)

if (!empty_nodes) mpr.boxplot(df.cluster06)

Localización geográfica de las estaciones de medida de cada cluster

# Agrupa por longitud y latitud para rellenar el mapa con menos datos.
if (!empty_nodes) {
  df.cluster01.grouped <- mpr.group_by_geo(df.cluster01)
  df.cluster02.grouped <- mpr.group_by_geo(df.cluster02)
  df.cluster03.grouped <- mpr.group_by_geo(df.cluster03)
  df.cluster04.grouped <- mpr.group_by_geo(df.cluster04)
  df.cluster05.grouped <- mpr.group_by_geo(df.cluster05)
  df.cluster06.grouped <- mpr.group_by_geo(df.cluster06)
}

if (!empty_nodes) mpr.draw_map(spain, df.cluster01.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster02.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster03.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster04.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster05.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster06.grouped)

Visualización de 8 clústeres:

if (!empty_nodes) {
  plot(hac, hang=-1, labels=F)
  rect.hclust(hac, k=8)
}

Visualización de los clústers en el mapa

A qué clúster pertenece cada nodo del mapa de kohonen:

if (!empty_nodes) {
  groups <- cutree(hac, k=8)
  plot(model, type="mapping",
    bgcol=c("steelblue1","sienna1","yellowgreen","red","blue","yellow","purple","green","white","#1f77b4", '#ff7f0e', '#2ca02c', '#d62728', '#9467bd', '#8c564b', '#e377c2')[groups],
    shape = "straight", labels = "")
  add.cluster.boundaries(model, clustering=groups)
}

Análisis de las observaciones de cada cluster

if (!empty_nodes) {
  # Asignamos a cada registro su clúster
  df$cluster <- groups[model$unit.classif]
}

Nuevos dataframes por cluster

if (!empty_nodes) {
  # Creo nuevos dataframes, uno por cada clúster.
  df.cluster01 <- subset(df, cluster==1)
  df.cluster02 <- subset(df, cluster==2)
  df.cluster03 <- subset(df, cluster==3)
  df.cluster04 <- subset(df, cluster==4)
  df.cluster05 <- subset(df, cluster==5)
  df.cluster06 <- subset(df, cluster==6)
  df.cluster07 <- subset(df, cluster==7)
  df.cluster08 <- subset(df, cluster==8)

  # Extraigo del dataframe las features.
  df.cluster01 <- select(df.cluster01, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster02 <- select(df.cluster02, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster03 <- select(df.cluster03, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster04 <- select(df.cluster04, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster05 <- select(df.cluster05, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster06 <- select(df.cluster06, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster07 <- select(df.cluster07, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster08 <- select(df.cluster08, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
}

if (!empty_nodes) summary(df.cluster01)

   fecha_cnt          tmax            tmin            precip            nevada 
 Min.   : 1.00   Min.   : -5.0   Min.   :-51.00   Min.   :  0.000   Min.   :0  
 1st Qu.:13.00   1st Qu.:101.0   1st Qu.: 27.00   1st Qu.:  0.000   1st Qu.:0  
 Median :26.00   Median :140.0   Median : 60.00   Median :  0.000   Median :0  
 Mean   :26.33   Mean   :144.1   Mean   : 67.88   Mean   :  9.353   Mean   :0  
 3rd Qu.:39.00   3rd Qu.:190.0   3rd Qu.:109.00   3rd Qu.:  3.000   3rd Qu.:0  
 Max.   :53.00   Max.   :263.0   Max.   :184.00   Max.   :316.000   Max.   :0  
   prof_nieve    longitud        latitud         altitud    
 Min.   :0    Min.   :28.31   Min.   :-16.5   Min.   :2371  
 1st Qu.:0    1st Qu.:28.31   1st Qu.:-16.5   1st Qu.:2371  
 Median :0    Median :28.31   Median :-16.5   Median :2371  
 Mean   :0    Mean   :28.31   Mean   :-16.5   Mean   :2371  
 3rd Qu.:0    3rd Qu.:28.31   3rd Qu.:-16.5   3rd Qu.:2371  
 Max.   :0    Max.   :28.31   Max.   :-16.5   Max.   :2371  

if (!empty_nodes) summary(df.cluster02)

   fecha_cnt          tmax            tmin            precip           nevada 
 Min.   : 1.00   Min.   : 66.0   Min.   :-29.00   Min.   :  0.00   Min.   :0  
 1st Qu.: 8.00   1st Qu.:158.0   1st Qu.: 56.00   1st Qu.:  0.00   1st Qu.:0  
 Median :13.00   Median :184.0   Median : 80.00   Median :  6.00   Median :0  
 Mean   :12.91   Mean   :187.5   Mean   : 82.26   Mean   : 19.13   Mean   :0  
 3rd Qu.:18.00   3rd Qu.:215.0   3rd Qu.:107.00   3rd Qu.: 25.00   3rd Qu.:0  
 Max.   :31.00   Max.   :327.0   Max.   :195.00   Max.   :523.00   Max.   :0  
   prof_nieve         longitud        latitud          altitud      
 Min.   :  0.000   Min.   :35.28   Min.   :-8.624   Min.   :   1.0  
 1st Qu.:  0.000   1st Qu.:38.88   1st Qu.:-4.846   1st Qu.:  32.0  
 Median :  0.000   Median :41.17   Median :-1.008   Median :  91.1  
 Mean   :  0.036   Mean   :40.49   Mean   :-1.596   Mean   : 246.4  
 3rd Qu.:  0.000   3rd Qu.:42.07   3rd Qu.: 1.384   3rd Qu.: 405.0  
 Max.   :164.000   Max.   :43.57   Max.   : 4.216   Max.   :1572.0  

if (!empty_nodes) summary(df.cluster03)

   fecha_cnt           tmax            tmin              precip      
 Min.   : 1.000   Min.   :-22.0   Min.   :-161.000   Min.   :  0.00  
 1st Qu.: 3.000   1st Qu.: 90.0   1st Qu.: -11.000   1st Qu.:  0.00  
 Median : 6.000   Median :112.0   Median :   9.000   Median :  7.00  
 Mean   : 6.667   Mean   :109.9   Mean   :   6.656   Mean   : 16.79  
 3rd Qu.: 9.000   3rd Qu.:132.0   3rd Qu.:  27.000   3rd Qu.: 22.00  
 Max.   :28.000   Max.   :200.0   Max.   :  84.000   Max.   :608.00  
     nevada    prof_nieve          longitud        latitud      
 Min.   :0   Min.   :  0.0000   Min.   :37.16   Min.   :-8.624  
 1st Qu.:0   1st Qu.:  0.0000   1st Qu.:40.70   1st Qu.:-3.789  
 Median :0   Median :  0.0000   Median :41.65   Median :-1.861  
 Mean   :0   Mean   :  0.3212   Mean   :41.39   Mean   :-1.517  
 3rd Qu.:0   3rd Qu.:  0.0000   3rd Qu.:42.22   3rd Qu.: 1.296  
 Max.   :0   Max.   :299.0000   Max.   :43.36   Max.   : 4.216  
    altitud      
 Min.   :   2.0  
 1st Qu.: 515.0  
 Median : 704.0  
 Mean   : 712.5  
 3rd Qu.: 900.0  
 Max.   :1894.0  

if (!empty_nodes) summary(df.cluster04)

   fecha_cnt          tmax            tmin           precip           nevada 
 Min.   : 1.00   Min.   :126.0   Min.   : 67.0   Min.   :  0.00   Min.   :0  
 1st Qu.:13.00   1st Qu.:218.0   1st Qu.:157.0   1st Qu.:  0.00   1st Qu.:0  
 Median :26.00   Median :239.0   Median :177.0   Median :  0.00   Median :0  
 Mean   :26.29   Mean   :240.5   Mean   :177.7   Mean   :  5.88   Mean   :0  
 3rd Qu.:39.00   3rd Qu.:265.0   3rd Qu.:205.0   3rd Qu.:  2.00   3rd Qu.:0  
 Max.   :53.00   Max.   :384.0   Max.   :263.0   Max.   :490.00   Max.   :0  
   prof_nieve    longitud        latitud          altitud     
 Min.   :0    Min.   :27.82   Min.   :-17.89   Min.   : 14.0  
 1st Qu.:0    1st Qu.:28.05   1st Qu.:-17.75   1st Qu.: 25.0  
 Median :0    Median :28.46   Median :-16.33   Median : 33.0  
 Mean   :0    Mean   :28.36   Mean   :-15.98   Mean   :110.7  
 3rd Qu.:0    3rd Qu.:28.63   3rd Qu.:-13.86   3rd Qu.: 64.0  
 Max.   :0    Max.   :28.95   Max.   :-13.60   Max.   :632.0  

if (!empty_nodes) summary(df.cluster05)

   fecha_cnt          tmax            tmin           precip            nevada 
 Min.   :14.00   Min.   :164.0   Min.   : 39.0   Min.   :  0.000   Min.   :0  
 1st Qu.:27.00   1st Qu.:262.0   1st Qu.:134.0   1st Qu.:  0.000   1st Qu.:0  
 Median :32.00   Median :289.0   Median :165.0   Median :  0.000   Median :0  
 Mean   :32.22   Mean   :288.5   Mean   :163.2   Mean   :  9.955   Mean   :0  
 3rd Qu.:37.00   3rd Qu.:315.0   3rd Qu.:191.0   3rd Qu.:  9.000   3rd Qu.:0  
 Max.   :53.00   Max.   :442.0   Max.   :272.0   Max.   :610.000   Max.   :0  
   prof_nieve          longitud        latitud           altitud      
 Min.   :  0.0000   Min.   :35.28   Min.   :-8.6239   Min.   :   1.0  
 1st Qu.:  0.0000   1st Qu.:38.99   1st Qu.:-3.7225   1st Qu.:  43.3  
 Median :  0.0000   Median :40.95   Median : 0.3264   Median : 247.0  
 Mean   :  0.0048   Mean   :40.33   Mean   :-0.9801   Mean   : 361.9  
 3rd Qu.:  0.0000   3rd Qu.:41.67   3rd Qu.: 1.4181   3rd Qu.: 628.0  
 Max.   :173.0000   Max.   :43.36   Max.   : 4.2156   Max.   :1894.0  

if (!empty_nodes) summary(df.cluster06)

   fecha_cnt          tmax            tmin           precip           nevada 
 Min.   :13.00   Min.   : 63.0   Min.   :-35.0   Min.   :  0.00   Min.   :0  
 1st Qu.:31.00   1st Qu.:170.0   1st Qu.: 87.0   1st Qu.:  1.00   1st Qu.:0  
 Median :42.00   Median :205.0   Median :120.0   Median : 11.00   Median :0  
 Mean   :39.25   Mean   :201.6   Mean   :114.9   Mean   : 28.26   Mean   :0  
 3rd Qu.:47.00   3rd Qu.:233.0   3rd Qu.:146.0   3rd Qu.: 38.00   3rd Qu.:0  
 Max.   :53.00   Max.   :346.0   Max.   :211.0   Max.   :422.00   Max.   :0  
   prof_nieve           longitud        latitud           altitud     
 Min.   :  0.00000   Min.   :35.28   Min.   :-8.6239   Min.   :  1.0  
 1st Qu.:  0.00000   1st Qu.:38.00   1st Qu.:-7.8603   1st Qu.: 42.0  
 Median :  0.00000   Median :42.89   Median :-6.0442   Median : 98.0  
 Mean   :  0.09183   Mean   :41.39   Mean   :-5.8760   Mean   :160.5  
 3rd Qu.:  0.00000   3rd Qu.:43.36   3rd Qu.:-3.8314   3rd Qu.:261.0  
 Max.   :290.00000   Max.   :43.57   Max.   : 0.8031   Max.   :916.0  

if (!empty_nodes) summary(df.cluster07)

   fecha_cnt          tmax              tmin             precip     
 Min.   : 1.00   Min.   :-109.00   Min.   :-189.00   Min.   :  0.0  
 1st Qu.:14.00   1st Qu.:  29.00   1st Qu.: -33.00   1st Qu.:  3.0  
 Median :27.00   Median :  76.00   Median :  10.00   Median : 19.0  
 Mean   :26.92   Mean   :  81.71   Mean   :  12.07   Mean   : 33.9  
 3rd Qu.:40.00   3rd Qu.: 136.00   3rd Qu.:  60.00   3rd Qu.: 48.0  
 Max.   :53.00   Max.   : 249.00   Max.   : 154.00   Max.   :615.0  
     nevada    prof_nieve          longitud        latitud       
 Min.   :0   Min.   :   0.000   Min.   :40.78   Min.   :-4.0103  
 1st Qu.:0   1st Qu.:   0.000   1st Qu.:42.18   1st Qu.: 0.7789  
 Median :0   Median :   0.000   Median :42.47   Median : 1.0544  
 Mean   :0   Mean   :   8.879   Mean   :42.25   Mean   : 0.7657  
 3rd Qu.:0   3rd Qu.:   0.000   3rd Qu.:42.64   3rd Qu.: 1.7150  
 Max.   :0   Max.   :1073.000   Max.   :42.77   Max.   : 2.4378  
    altitud    
 Min.   :1056  
 1st Qu.:1971  
 Median :2230  
 Mean   :2157  
 3rd Qu.:2400  
 Max.   :2535  

if (!empty_nodes) summary(df.cluster08)

   fecha_cnt         tmax            tmin             precip           nevada 
 Min.   :29.0   Min.   :-31.0   Min.   :-155.00   Min.   :  0.00   Min.   :0  
 1st Qu.:44.0   1st Qu.:115.0   1st Qu.:  20.00   1st Qu.:  0.00   1st Qu.:0  
 Median :47.0   Median :149.0   Median :  50.00   Median :  4.00   Median :0  
 Mean   :46.8   Mean   :148.3   Mean   :  46.88   Mean   : 17.06   Mean   :0  
 3rd Qu.:50.0   3rd Qu.:181.0   3rd Qu.:  77.00   3rd Qu.: 21.00   3rd Qu.:0  
 Max.   :53.0   Max.   :286.0   Max.   : 144.00   Max.   :690.00   Max.   :0  
   prof_nieve           longitud        latitud           altitud      
 Min.   :  0.00000   Min.   :37.19   Min.   :-8.4106   Min.   :   1.0  
 1st Qu.:  0.00000   1st Qu.:40.70   1st Qu.:-3.1742   1st Qu.: 192.0  
 Median :  0.00000   Median :41.48   Median : 0.3994   Median : 594.0  
 Mean   :  0.06704   Mean   :41.23   Mean   :-0.6194   Mean   : 544.3  
 3rd Qu.:  0.00000   3rd Qu.:42.07   3rd Qu.: 1.6531   3rd Qu.: 846.0  
 Max.   :148.00000   Max.   :43.43   Max.   : 4.2156   Max.   :1572.0  

Número de elementos en cada clúster

if (!empty_nodes) {
  df.clusters.dim <- c(dim(df.cluster01)[1], dim(df.cluster02)[1], dim(df.cluster03)[1], dim(df.cluster04)[1], dim(df.cluster05)[1], dim(df.cluster06)[1], dim(df.cluster07)[1], dim(df.cluster08)[1])
  barplot(df.clusters.dim,
          names.arg = c("cluster01", "cluster02", "cluster03", "cluster04", "cluster05", "cluster06", "cluster07", "cluster08"),
          col = "steelblue1")
}

Distribución de los datos

if (!empty_nodes) mpr.hist(df.cluster01)

if (!empty_nodes) mpr.hist(df.cluster02)

if (!empty_nodes) mpr.hist(df.cluster03)

if (!empty_nodes) mpr.hist(df.cluster04)

if (!empty_nodes) mpr.hist(df.cluster05)

if (!empty_nodes) mpr.hist(df.cluster06)

if (!empty_nodes) mpr.hist(df.cluster07)

if (!empty_nodes) mpr.hist(df.cluster08)

if (!empty_nodes) mpr.boxplot(df.cluster01)
if (!empty_nodes) mpr.boxplot(df.cluster02)

if (!empty_nodes) mpr.boxplot(df.cluster03)

if (!empty_nodes) mpr.boxplot(df.cluster04)

if (!empty_nodes) mpr.boxplot(df.cluster05)

if (!empty_nodes) mpr.boxplot(df.cluster06)

if (!empty_nodes) mpr.boxplot(df.cluster07)

if (!empty_nodes) mpr.boxplot(df.cluster08)

Localización geográfica de las estaciones de medida de cada cluster

# Agrupa por longitud y latitud para rellenar el mapa con menos datos.
if (!empty_nodes) {
  df.cluster01.grouped <- mpr.group_by_geo(df.cluster01)
  df.cluster02.grouped <- mpr.group_by_geo(df.cluster02)
  df.cluster03.grouped <- mpr.group_by_geo(df.cluster03)
  df.cluster04.grouped <- mpr.group_by_geo(df.cluster04)
  df.cluster05.grouped <- mpr.group_by_geo(df.cluster05)
  df.cluster06.grouped <- mpr.group_by_geo(df.cluster06)
  df.cluster07.grouped <- mpr.group_by_geo(df.cluster07)
  df.cluster08.grouped <- mpr.group_by_geo(df.cluster08)
}

if (!empty_nodes) mpr.draw_map(spain, df.cluster01.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster02.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster03.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster04.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster05.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster06.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster07.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster08.grouped)

Visualización de 10 clústeres:

if (!empty_nodes) {
  plot(hac, hang=-1, labels=F)
  rect.hclust(hac, k=10)
}

Visualización de los clústers en el mapa

A qué clúster pertenece cada nodo del mapa de kohonen:

if (!empty_nodes) {
  groups <- cutree(hac, k=10)
  plot(model, type="mapping",
    bgcol=c("steelblue1","sienna1","yellowgreen","red","blue","yellow","purple","green","white","#1f77b4", '#ff7f0e', '#2ca02c', '#d62728', '#9467bd', '#8c564b', '#e377c2')[groups],
    shape = "straight", labels = "")
  add.cluster.boundaries(model, clustering=groups)
}

Análisis de las observaciones de cada cluster

if (!empty_nodes) {
  # Asignamos a cada registro su clúster
  df$cluster <- groups[model$unit.classif]
}

Nuevos dataframes por cluster

if (!empty_nodes) {
  # Creo nuevos dataframes, uno por cada clúster.
  df.cluster01 <- subset(df, cluster==1)
  df.cluster02 <- subset(df, cluster==2)
  df.cluster03 <- subset(df, cluster==3)
  df.cluster04 <- subset(df, cluster==4)
  df.cluster05 <- subset(df, cluster==5)
  df.cluster06 <- subset(df, cluster==6)
  df.cluster07 <- subset(df, cluster==7)
  df.cluster08 <- subset(df, cluster==8)
  df.cluster09 <- subset(df, cluster==9)
  df.cluster10 <- subset(df, cluster==10)

  # Extraigo del dataframe las features.
  df.cluster01 <- select(df.cluster01, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster02 <- select(df.cluster02, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster03 <- select(df.cluster03, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster04 <- select(df.cluster04, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster05 <- select(df.cluster05, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster06 <- select(df.cluster06, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster07 <- select(df.cluster07, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster08 <- select(df.cluster08, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster09 <- select(df.cluster09, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster10 <- select(df.cluster10, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
}

if (!empty_nodes) summary(df.cluster01)

   fecha_cnt          tmax            tmin            precip            nevada 
 Min.   : 1.00   Min.   : -5.0   Min.   :-51.00   Min.   :  0.000   Min.   :0  
 1st Qu.:13.00   1st Qu.:101.0   1st Qu.: 27.00   1st Qu.:  0.000   1st Qu.:0  
 Median :26.00   Median :140.0   Median : 60.00   Median :  0.000   Median :0  
 Mean   :26.33   Mean   :144.1   Mean   : 67.88   Mean   :  9.353   Mean   :0  
 3rd Qu.:39.00   3rd Qu.:190.0   3rd Qu.:109.00   3rd Qu.:  3.000   3rd Qu.:0  
 Max.   :53.00   Max.   :263.0   Max.   :184.00   Max.   :316.000   Max.   :0  
   prof_nieve    longitud        latitud         altitud    
 Min.   :0    Min.   :28.31   Min.   :-16.5   Min.   :2371  
 1st Qu.:0    1st Qu.:28.31   1st Qu.:-16.5   1st Qu.:2371  
 Median :0    Median :28.31   Median :-16.5   Median :2371  
 Mean   :0    Mean   :28.31   Mean   :-16.5   Mean   :2371  
 3rd Qu.:0    3rd Qu.:28.31   3rd Qu.:-16.5   3rd Qu.:2371  
 Max.   :0    Max.   :28.31   Max.   :-16.5   Max.   :2371  

if (!empty_nodes) summary(df.cluster02)

   fecha_cnt          tmax            tmin            precip           nevada 
 Min.   : 1.00   Min.   : 86.0   Min.   :-29.00   Min.   :  0.00   Min.   :0  
 1st Qu.: 6.00   1st Qu.:171.0   1st Qu.: 73.00   1st Qu.:  0.00   1st Qu.:0  
 Median :12.00   Median :196.0   Median :101.00   Median :  2.00   Median :0  
 Mean   :11.81   Mean   :201.3   Mean   : 99.69   Mean   : 15.17   Mean   :0  
 3rd Qu.:17.00   3rd Qu.:229.0   3rd Qu.:128.00   3rd Qu.: 19.00   3rd Qu.:0  
 Max.   :27.00   Max.   :327.0   Max.   :195.00   Max.   :354.00   Max.   :0  
   prof_nieve          longitud        latitud          altitud     
 Min.   : 0.00000   Min.   :35.28   Min.   :-6.949   Min.   :  1.0  
 1st Qu.: 0.00000   1st Qu.:36.64   1st Qu.:-6.257   1st Qu.: 21.0  
 Median : 0.00000   Median :37.16   Median :-5.598   Median : 47.0  
 Mean   : 0.00964   Mean   :37.12   Mean   :-4.867   Mean   :110.6  
 3rd Qu.: 0.00000   3rd Qu.:37.78   3rd Qu.:-3.789   3rd Qu.: 90.0  
 Max.   :10.00000   Max.   :39.88   Max.   :-0.500   Max.   :717.0  

if (!empty_nodes) summary(df.cluster03)

   fecha_cnt          tmax          tmin           precip           nevada 
 Min.   : 1.00   Min.   : 66   Min.   :-29.0   Min.   :  0.00   Min.   :0  
 1st Qu.: 9.00   1st Qu.:155   1st Qu.: 53.0   1st Qu.:  0.00   1st Qu.:0  
 Median :14.00   Median :180   Median : 75.0   Median :  7.00   Median :0  
 Mean   :13.18   Mean   :184   Mean   : 77.9   Mean   : 20.13   Mean   :0  
 3rd Qu.:18.00   3rd Qu.:212   3rd Qu.:100.0   3rd Qu.: 27.00   3rd Qu.:0  
 Max.   :31.00   Max.   :322   Max.   :187.0   Max.   :523.00   Max.   :0  
   prof_nieve           longitud        latitud           altitud      
 Min.   :  0.00000   Min.   :37.78   Min.   :-8.6239   Min.   :   1.0  
 1st Qu.:  0.00000   1st Qu.:40.71   1st Qu.:-2.9056   1st Qu.:  43.0  
 Median :  0.00000   Median :41.52   Median : 0.5356   Median : 147.0  
 Mean   :  0.04261   Mean   :41.34   Mean   :-0.7769   Mean   : 280.4  
 3rd Qu.:  0.00000   3rd Qu.:42.27   3rd Qu.: 1.8081   3rd Qu.: 445.0  
 Max.   :164.00000   Max.   :43.57   Max.   : 4.2156   Max.   :1572.0  

if (!empty_nodes) summary(df.cluster04)

   fecha_cnt           tmax            tmin              precip      
 Min.   : 1.000   Min.   :-22.0   Min.   :-161.000   Min.   :  0.00  
 1st Qu.: 3.000   1st Qu.: 90.0   1st Qu.: -11.000   1st Qu.:  0.00  
 Median : 6.000   Median :112.0   Median :   9.000   Median :  7.00  
 Mean   : 6.667   Mean   :109.9   Mean   :   6.656   Mean   : 16.79  
 3rd Qu.: 9.000   3rd Qu.:132.0   3rd Qu.:  27.000   3rd Qu.: 22.00  
 Max.   :28.000   Max.   :200.0   Max.   :  84.000   Max.   :608.00  
     nevada    prof_nieve          longitud        latitud      
 Min.   :0   Min.   :  0.0000   Min.   :37.16   Min.   :-8.624  
 1st Qu.:0   1st Qu.:  0.0000   1st Qu.:40.70   1st Qu.:-3.789  
 Median :0   Median :  0.0000   Median :41.65   Median :-1.861  
 Mean   :0   Mean   :  0.3212   Mean   :41.39   Mean   :-1.517  
 3rd Qu.:0   3rd Qu.:  0.0000   3rd Qu.:42.22   3rd Qu.: 1.296  
 Max.   :0   Max.   :299.0000   Max.   :43.36   Max.   : 4.216  
    altitud      
 Min.   :   2.0  
 1st Qu.: 515.0  
 Median : 704.0  
 Mean   : 712.5  
 3rd Qu.: 900.0  
 Max.   :1894.0  

if (!empty_nodes) summary(df.cluster05)

   fecha_cnt          tmax            tmin           precip           nevada 
 Min.   : 1.00   Min.   :126.0   Min.   : 67.0   Min.   :  0.00   Min.   :0  
 1st Qu.:13.00   1st Qu.:218.0   1st Qu.:157.0   1st Qu.:  0.00   1st Qu.:0  
 Median :26.00   Median :239.0   Median :177.0   Median :  0.00   Median :0  
 Mean   :26.29   Mean   :240.5   Mean   :177.7   Mean   :  5.88   Mean   :0  
 3rd Qu.:39.00   3rd Qu.:265.0   3rd Qu.:205.0   3rd Qu.:  2.00   3rd Qu.:0  
 Max.   :53.00   Max.   :384.0   Max.   :263.0   Max.   :490.00   Max.   :0  
   prof_nieve    longitud        latitud          altitud     
 Min.   :0    Min.   :27.82   Min.   :-17.89   Min.   : 14.0  
 1st Qu.:0    1st Qu.:28.05   1st Qu.:-17.75   1st Qu.: 25.0  
 Median :0    Median :28.46   Median :-16.33   Median : 33.0  
 Mean   :0    Mean   :28.36   Mean   :-15.98   Mean   :110.7  
 3rd Qu.:0    3rd Qu.:28.63   3rd Qu.:-13.86   3rd Qu.: 64.0  
 Max.   :0    Max.   :28.95   Max.   :-13.60   Max.   :632.0  

if (!empty_nodes) summary(df.cluster06)

   fecha_cnt          tmax            tmin           precip            nevada 
 Min.   :14.00   Min.   :164.0   Min.   : 39.0   Min.   :  0.000   Min.   :0  
 1st Qu.:27.00   1st Qu.:262.0   1st Qu.:134.0   1st Qu.:  0.000   1st Qu.:0  
 Median :32.00   Median :289.0   Median :165.0   Median :  0.000   Median :0  
 Mean   :32.22   Mean   :288.5   Mean   :163.2   Mean   :  9.955   Mean   :0  
 3rd Qu.:37.00   3rd Qu.:315.0   3rd Qu.:191.0   3rd Qu.:  9.000   3rd Qu.:0  
 Max.   :53.00   Max.   :442.0   Max.   :272.0   Max.   :610.000   Max.   :0  
   prof_nieve          longitud        latitud           altitud      
 Min.   :  0.0000   Min.   :35.28   Min.   :-8.6239   Min.   :   1.0  
 1st Qu.:  0.0000   1st Qu.:38.99   1st Qu.:-3.7225   1st Qu.:  43.3  
 Median :  0.0000   Median :40.95   Median : 0.3264   Median : 247.0  
 Mean   :  0.0048   Mean   :40.33   Mean   :-0.9801   Mean   : 361.9  
 3rd Qu.:  0.0000   3rd Qu.:41.67   3rd Qu.: 1.4181   3rd Qu.: 628.0  
 Max.   :173.0000   Max.   :43.36   Max.   : 4.2156   Max.   :1894.0  

if (!empty_nodes) summary(df.cluster07)

   fecha_cnt          tmax            tmin           precip           nevada 
 Min.   :13.00   Min.   : 63.0   Min.   :-35.0   Min.   :  0.00   Min.   :0  
 1st Qu.:31.00   1st Qu.:170.0   1st Qu.: 87.0   1st Qu.:  1.00   1st Qu.:0  
 Median :42.00   Median :205.0   Median :120.0   Median : 11.00   Median :0  
 Mean   :39.25   Mean   :201.6   Mean   :114.9   Mean   : 28.26   Mean   :0  
 3rd Qu.:47.00   3rd Qu.:233.0   3rd Qu.:146.0   3rd Qu.: 38.00   3rd Qu.:0  
 Max.   :53.00   Max.   :346.0   Max.   :211.0   Max.   :422.00   Max.   :0  
   prof_nieve           longitud        latitud           altitud     
 Min.   :  0.00000   Min.   :35.28   Min.   :-8.6239   Min.   :  1.0  
 1st Qu.:  0.00000   1st Qu.:38.00   1st Qu.:-7.8603   1st Qu.: 42.0  
 Median :  0.00000   Median :42.89   Median :-6.0442   Median : 98.0  
 Mean   :  0.09183   Mean   :41.39   Mean   :-5.8760   Mean   :160.5  
 3rd Qu.:  0.00000   3rd Qu.:43.36   3rd Qu.:-3.8314   3rd Qu.:261.0  
 Max.   :290.00000   Max.   :43.57   Max.   : 0.8031   Max.   :916.0  

if (!empty_nodes) summary(df.cluster08)

   fecha_cnt          tmax            tmin             precip           nevada 
 Min.   : 1.00   Min.   :-79.0   Min.   :-146.00   Min.   :  0.00   Min.   :0  
 1st Qu.:28.00   1st Qu.: 65.0   1st Qu.:   5.00   1st Qu.:  3.00   1st Qu.:0  
 Median :37.00   Median :119.0   Median :  48.00   Median : 16.00   Median :0  
 Mean   :36.33   Mean   :111.4   Mean   :  39.91   Mean   : 30.96   Mean   :0  
 3rd Qu.:45.00   3rd Qu.:159.0   3rd Qu.:  80.00   3rd Qu.: 42.00   3rd Qu.:0  
 Max.   :53.00   Max.   :249.0   Max.   : 154.00   Max.   :459.00   Max.   :0  
   prof_nieve         longitud        latitud           altitud    
 Min.   :  0.000   Min.   :40.78   Min.   :-4.0103   Min.   :1405  
 1st Qu.:  0.000   1st Qu.:42.18   1st Qu.: 0.7789   1st Qu.:1894  
 Median :  0.000   Median :42.47   Median : 1.0544   Median :2230  
 Mean   :  2.267   Mean   :42.23   Mean   : 0.7696   Mean   :2136  
 3rd Qu.:  0.000   3rd Qu.:42.64   3rd Qu.: 1.7150   3rd Qu.:2400  
 Max.   :805.000   Max.   :42.77   Max.   : 2.4378   Max.   :2535  

if (!empty_nodes) summary(df.cluster09)

   fecha_cnt          tmax              tmin             precip     
 Min.   : 1.00   Min.   :-109.00   Min.   :-189.00   Min.   :  0.0  
 1st Qu.: 5.00   1st Qu.:   4.00   1st Qu.: -60.00   1st Qu.:  6.0  
 Median :10.00   Median :  33.00   Median : -32.00   Median : 25.0  
 Mean   :10.55   Mean   :  30.13   Mean   : -36.36   Mean   : 39.0  
 3rd Qu.:15.00   3rd Qu.:  61.00   3rd Qu.:  -7.00   3rd Qu.: 55.5  
 Max.   :26.00   Max.   : 132.00   Max.   :  56.00   Max.   :615.0  
     nevada    prof_nieve         longitud        latitud           altitud    
 Min.   :0   Min.   :   0.00   Min.   :40.78   Min.   :-4.0103   Min.   :1056  
 1st Qu.:0   1st Qu.:   0.00   1st Qu.:42.18   1st Qu.: 0.7789   1st Qu.:1971  
 Median :0   Median :   0.00   Median :42.47   Median : 1.0544   Median :2247  
 Mean   :0   Mean   :  20.38   Mean   :42.28   Mean   : 0.7588   Mean   :2195  
 3rd Qu.:0   3rd Qu.:   0.00   3rd Qu.:42.64   3rd Qu.: 1.7150   3rd Qu.:2400  
 Max.   :0   Max.   :1073.00   Max.   :42.77   Max.   : 2.4378   Max.   :2535  

if (!empty_nodes) summary(df.cluster10)

   fecha_cnt         tmax            tmin             precip           nevada 
 Min.   :29.0   Min.   :-31.0   Min.   :-155.00   Min.   :  0.00   Min.   :0  
 1st Qu.:44.0   1st Qu.:115.0   1st Qu.:  20.00   1st Qu.:  0.00   1st Qu.:0  
 Median :47.0   Median :149.0   Median :  50.00   Median :  4.00   Median :0  
 Mean   :46.8   Mean   :148.3   Mean   :  46.88   Mean   : 17.06   Mean   :0  
 3rd Qu.:50.0   3rd Qu.:181.0   3rd Qu.:  77.00   3rd Qu.: 21.00   3rd Qu.:0  
 Max.   :53.0   Max.   :286.0   Max.   : 144.00   Max.   :690.00   Max.   :0  
   prof_nieve           longitud        latitud           altitud      
 Min.   :  0.00000   Min.   :37.19   Min.   :-8.4106   Min.   :   1.0  
 1st Qu.:  0.00000   1st Qu.:40.70   1st Qu.:-3.1742   1st Qu.: 192.0  
 Median :  0.00000   Median :41.48   Median : 0.3994   Median : 594.0  
 Mean   :  0.06704   Mean   :41.23   Mean   :-0.6194   Mean   : 544.3  
 3rd Qu.:  0.00000   3rd Qu.:42.07   3rd Qu.: 1.6531   3rd Qu.: 846.0  
 Max.   :148.00000   Max.   :43.43   Max.   : 4.2156   Max.   :1572.0  

Número de elementos en cada clúster

if (!empty_nodes) {
  df.clusters.dim <- c(dim(df.cluster01)[1], dim(df.cluster02)[1], dim(df.cluster03)[1], dim(df.cluster04)[1], dim(df.cluster05)[1], dim(df.cluster06)[1], dim(df.cluster07)[1], dim(df.cluster08)[1], dim(df.cluster09)[1], dim(df.cluster10)[1])
  barplot(df.clusters.dim,
          names.arg = c("cluster01", "cluster02", "cluster03", "cluster04", "cluster05", "cluster06", "cluster07", "cluster08", "cluster09", "cluster10"),
          col = "steelblue1")
}

Distribución de los datos

if (!empty_nodes) mpr.hist(df.cluster01)

if (!empty_nodes) mpr.hist(df.cluster02)

if (!empty_nodes) mpr.hist(df.cluster03)

if (!empty_nodes) mpr.hist(df.cluster04)

if (!empty_nodes) mpr.hist(df.cluster05)

if (!empty_nodes) mpr.hist(df.cluster06)

if (!empty_nodes) mpr.hist(df.cluster07)

if (!empty_nodes) mpr.hist(df.cluster08)

if (!empty_nodes) mpr.hist(df.cluster09)

if (!empty_nodes) mpr.hist(df.cluster10)

if (!empty_nodes) mpr.boxplot(df.cluster01)
if (!empty_nodes) mpr.boxplot(df.cluster02)

if (!empty_nodes) mpr.boxplot(df.cluster03)

if (!empty_nodes) mpr.boxplot(df.cluster04)

if (!empty_nodes) mpr.boxplot(df.cluster05)

if (!empty_nodes) mpr.boxplot(df.cluster06)

if (!empty_nodes) mpr.boxplot(df.cluster07)

if (!empty_nodes) mpr.boxplot(df.cluster08)

if (!empty_nodes) mpr.boxplot(df.cluster09)

if (!empty_nodes) mpr.boxplot(df.cluster10)

Localización geográfica de las estaciones de medida de cada cluster

# Agrupa por longitud y latitud para rellenar el mapa con menos datos.
if (!empty_nodes) {
  df.cluster01.grouped <- mpr.group_by_geo(df.cluster01)
  df.cluster02.grouped <- mpr.group_by_geo(df.cluster02)
  df.cluster03.grouped <- mpr.group_by_geo(df.cluster03)
  df.cluster04.grouped <- mpr.group_by_geo(df.cluster04)
  df.cluster05.grouped <- mpr.group_by_geo(df.cluster05)
  df.cluster06.grouped <- mpr.group_by_geo(df.cluster06)
  df.cluster07.grouped <- mpr.group_by_geo(df.cluster07)
  df.cluster08.grouped <- mpr.group_by_geo(df.cluster08)
  df.cluster09.grouped <- mpr.group_by_geo(df.cluster09)
  df.cluster10.grouped <- mpr.group_by_geo(df.cluster10)
}

if (!empty_nodes) mpr.draw_map(spain, df.cluster01.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster02.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster03.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster04.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster05.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster06.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster07.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster08.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster09.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster10.grouped)